- Home
- Skills
- APIs & Backend
- Quadruped Robot Dog Engineering
Quadruped Robot Dog Engineering
Program and deploy quadruped robots using ROS 2, high-level motion APIs, and safety-validated autonomous navigation.
$39
Works with the AI Agents you already use
Quadruped Robot Dog Engineering
Example session with this skill installed
Help me set up a ROS 2 based autonomous patrol for a Unitree Go2. It needs to navigate between three waypoints on a flat floor and stop if the battery drops below 20%.
- Read your context and instructions
- Compiled the quadruped robot dog
I have outlined the configuration for a ROS 2 autonomous patrol mission on the Unitree Go2. This setup uses the high-level sport mode via the SDK2 bridge, integrated with Nav2 for waypoint sequencing and a battery monitor node for safety. ## Autonomous Patrol Configuration | Component | Implementation Detail | | :--- | :--- | | **Communication** | CycloneDDS configured for Unitree SDK2 (DDS Domain 0) | | **State Estimation** | `/utree/sport/odom` -> `slam_toolbox` (Asynchronous mode) | | **Motion Controller** | Nav2 `ControllerServer` using `DWBLocalPlanner` with holonomic constraints | | **Velocity Limits** | Max Linear: 0.5 m/s, Max Angular: 0.4 rad/s | | **Battery Logic** | `BatteryState` subscriber triggers `cmd_vel` timeout and `nav_to_pose` (Dock) | | **Safety** | `collision_monitor` node with 0.5m stop zone | ```python # patrol_mission.py import rclpy from unitree_sdk2py.go2.sport.sport_client import SportClient def battery_callback(msg): # Threshold check for safety return if msg.voltage < 20.0: stop_patrol_and_return_home() def execute_patrol(waypoints): client = SportClient() for point in waypoints: # High-level motion API client.MoveTo(point.x, point.y, point.yaw) # Verify arrival via odom before next waypoint wait_for_arrival(point) ``` **Next steps** 1. Test the emergency stop (e-stop) functionality in the Unitree app before launching the ROS bridge. 2. Calibrate the IMU and ensure the Go2 is on a level surface in a cleared 2m radius. 3. Verify the DDS connection by echoing the `/joint_states` topic to ensure telemetry is flowing.
Connects securely to your tools. The creator never sees your data.
About this skill
High-level to joint-level: MPC/WBC, state estimation, missions. Program a quadruped robot dog (Unitree Go2/B2, Boston Dynamics Spot, DEEP Robotics, open-source dogs) - high-level motion API, ROS 2 integration, SLAM and autonomous patrols with Nav2, payloads and perception, low-level joint control for custom controllers, and safe operating procedures. Use when the user wants a robot dog to walk routes, inspect a site, follow a person, carry sensors, run a custom gait, or integrate with ROS 2 / an AI agent. Includes an EXPERT.md reference (exact parameters, thresholds, failure diagnosis). Acceptable use: civil and commercial applications only. Any military, paramilitary or weapon-related use is prohibited, as stated in the skill itself.
Requires physical e-stop and supervision. Low-level control requires a harness/gantry. Military and weaponized applications are strictly prohibited.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 28 days ago